TY - JOUR
T1 - Deep learning speeds up ice flow modelling by several orders of magnitude
AU - Jouvet, Guillaume
AU - Cordonnier, Guillaume
AU - Kim, Byungsoo
AU - Lüthi, Martin
AU - Vieli, Andreas
AU - Aschwanden, Andy
N1 - Publisher Copyright:
Copyright © The Author(s), 2021. Published by Cambridge University Press.
PY - 2022/8/22
Y1 - 2022/8/22
N2 - This paper introduces the Instructed Glacier Model (IGM) - a model that simulates ice dynamics, mass balance and its coupling to predict the evolution of glaciers, icefields or ice sheets. The novelty of IGM is that it models the ice flow by a Convolutional Neural Network, which is trained from data generated with hybrid SIA + SSA or Stokes ice flow models. By doing so, the most computationally demanding model component is substituted by a cheap emulator. Once trained with representative data, we demonstrate that IGM permits to model mountain glaciers up to 1000 × faster than Stokes ones on Central Processing Units (CPU) with fidelity levels above 90% in terms of ice flow solutions leading to nearly identical transient thickness evolution. Switching to the GPU often permits additional significant speed-ups, especially when emulating Stokes dynamics or/and modelling at high spatial resolution. IGM is an open-source Python code which deals with two-dimensional (2-D) gridded input and output data. Together with a companion library of trained ice flow emulators, IGM permits user-friendly, highly efficient and mechanically state-of-the-art glacier and icefields simulations.
AB - This paper introduces the Instructed Glacier Model (IGM) - a model that simulates ice dynamics, mass balance and its coupling to predict the evolution of glaciers, icefields or ice sheets. The novelty of IGM is that it models the ice flow by a Convolutional Neural Network, which is trained from data generated with hybrid SIA + SSA or Stokes ice flow models. By doing so, the most computationally demanding model component is substituted by a cheap emulator. Once trained with representative data, we demonstrate that IGM permits to model mountain glaciers up to 1000 × faster than Stokes ones on Central Processing Units (CPU) with fidelity levels above 90% in terms of ice flow solutions leading to nearly identical transient thickness evolution. Switching to the GPU often permits additional significant speed-ups, especially when emulating Stokes dynamics or/and modelling at high spatial resolution. IGM is an open-source Python code which deals with two-dimensional (2-D) gridded input and output data. Together with a companion library of trained ice flow emulators, IGM permits user-friendly, highly efficient and mechanically state-of-the-art glacier and icefields simulations.
KW - Glacier flow
KW - glacier modelling
KW - ice dynamics
KW - ice velocity
UR - http://www.scopus.com/inward/record.url?scp=85121799927&partnerID=8YFLogxK
U2 - 10.1017/jog.2021.120
DO - 10.1017/jog.2021.120
M3 - Article
AN - SCOPUS:85121799927
SN - 0022-1430
VL - 68
SP - 651
EP - 664
JO - Journal of Glaciology
JF - Journal of Glaciology
IS - 270
ER -